PHARAOH: A collaborative crowdsourcing platform for phenotyping and regional analysis of histology

Abstract Deep learning has proven capable of automating key aspects of histopathologic analysis. However, its context-specific nature and continued reliance on large expert-annotated training datasets hinders the development of a critical mass of applications to garner widespread adoption in clinica...

Full description

Saved in:
Bibliographic Details
Main Authors: Kevin Faust, Min Li Chen, Parsa Babaei Zadeh, Dimitrios G. Oreopoulos, Alberto J. Leon, Ameesha Paliwal, Evelyn Rose Kamski-Hennekam, Marly Mikhail, Xianpi Duan, Xianzhao Duan, Mugeng Liu, Narges Ahangari, Raul Cotau, Vincent Francis Castillo, Nikfar Nikzad, Richard J. Sugden, Patrick Murphy, Safiyh S. Aljohani, Philippe Echelard, Susan J. Done, Kiran Jakate, Zaid Saeed Kamil, Yazeed Alwelaie, Mohammed J. Alyousef, Noor Said Alsafwani, Assem Saleh Alrumeh, Rola M. Saleeb, Maxime Richer, Lidiane Vieira Marins, George M. Yousef, Phedias Diamandis
Format: Article
Language:English
Published: Nature Portfolio 2025-01-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-024-55780-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832594599953039360
author Kevin Faust
Min Li Chen
Parsa Babaei Zadeh
Dimitrios G. Oreopoulos
Alberto J. Leon
Ameesha Paliwal
Evelyn Rose Kamski-Hennekam
Marly Mikhail
Xianpi Duan
Xianzhao Duan
Mugeng Liu
Narges Ahangari
Raul Cotau
Vincent Francis Castillo
Nikfar Nikzad
Richard J. Sugden
Patrick Murphy
Safiyh S. Aljohani
Philippe Echelard
Susan J. Done
Kiran Jakate
Zaid Saeed Kamil
Yazeed Alwelaie
Mohammed J. Alyousef
Noor Said Alsafwani
Assem Saleh Alrumeh
Rola M. Saleeb
Maxime Richer
Lidiane Vieira Marins
George M. Yousef
Phedias Diamandis
author_facet Kevin Faust
Min Li Chen
Parsa Babaei Zadeh
Dimitrios G. Oreopoulos
Alberto J. Leon
Ameesha Paliwal
Evelyn Rose Kamski-Hennekam
Marly Mikhail
Xianpi Duan
Xianzhao Duan
Mugeng Liu
Narges Ahangari
Raul Cotau
Vincent Francis Castillo
Nikfar Nikzad
Richard J. Sugden
Patrick Murphy
Safiyh S. Aljohani
Philippe Echelard
Susan J. Done
Kiran Jakate
Zaid Saeed Kamil
Yazeed Alwelaie
Mohammed J. Alyousef
Noor Said Alsafwani
Assem Saleh Alrumeh
Rola M. Saleeb
Maxime Richer
Lidiane Vieira Marins
George M. Yousef
Phedias Diamandis
author_sort Kevin Faust
collection DOAJ
description Abstract Deep learning has proven capable of automating key aspects of histopathologic analysis. However, its context-specific nature and continued reliance on large expert-annotated training datasets hinders the development of a critical mass of applications to garner widespread adoption in clinical/research workflows. Here, we present an online collaborative platform that streamlines tissue image annotation to promote the development and sharing of custom computer vision models for PHenotyping And Regional Analysis Of Histology (PHARAOH; https://www.pathologyreports.ai/ ). Specifically, PHARAOH uses a weakly supervised, human-in-the-loop learning framework whereby patch-level image features are leveraged to organize large swaths of tissue into morphologically-uniform clusters for batched annotation by human experts. By providing cluster-level labels on only a handful of cases, we show how custom PHARAOH models can be developed efficiently and used to guide the quantification of cellular features that correlate with molecular, pathologic and patient outcome data. Moreover, by using our PHARAOH pipeline, we showcase how correlation of cohort-level cytoarchitectural features with accompanying biological and outcome data can help systematically devise interpretable morphometric models of disease. Both the custom model design and feature extraction pipelines are amenable to crowdsourcing, positioning PHARAOH to become a fully scalable, systems-level solution for the expansion, generalization and cataloging of computational pathology applications.
format Article
id doaj-art-11156d46defe4bacbd6d8e9c2895fe18
institution Kabale University
issn 2041-1723
language English
publishDate 2025-01-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-11156d46defe4bacbd6d8e9c2895fe182025-01-19T12:29:52ZengNature PortfolioNature Communications2041-17232025-01-0116111210.1038/s41467-024-55780-zPHARAOH: A collaborative crowdsourcing platform for phenotyping and regional analysis of histologyKevin Faust0Min Li Chen1Parsa Babaei Zadeh2Dimitrios G. Oreopoulos3Alberto J. Leon4Ameesha Paliwal5Evelyn Rose Kamski-Hennekam6Marly Mikhail7Xianpi Duan8Xianzhao Duan9Mugeng Liu10Narges Ahangari11Raul Cotau12Vincent Francis Castillo13Nikfar Nikzad14Richard J. Sugden15Patrick Murphy16Safiyh S. Aljohani17Philippe Echelard18Susan J. Done19Kiran Jakate20Zaid Saeed Kamil21Yazeed Alwelaie22Mohammed J. Alyousef23Noor Said Alsafwani24Assem Saleh Alrumeh25Rola M. Saleeb26Maxime Richer27Lidiane Vieira Marins28George M. Yousef29Phedias Diamandis30Princess Margaret Cancer CentrePrincess Margaret Cancer CentrePrincess Margaret Cancer CentrePrincess Margaret Cancer CentrePrincess Margaret Cancer CentrePrincess Margaret Cancer CentrePrincess Margaret Cancer CentrePrincess Margaret Cancer CentreDepartment of Computing and Software, McMaster UniversityDepartment of Computing and Software, McMaster UniversityPrincess Margaret Cancer CentreDepartment of Laboratory Medicine and Pathobiology, University of TorontoAxe neurosciences du Centre de recherche du Centre hospitalier universitaire (CHU) de Québec-Université Laval, et Département de biologie moléculaire, biochimie et pathologie de l’Université LavalDepartment of Laboratory Medicine and Pathobiology, University of TorontoDepartment of Pathology and Molecular Medicine, McMaster UniversityPrincess Margaret Cancer CentreDepartment of Laboratory Medicine and Pathobiology, University of TorontoDepartment of Pathology, College of Medicine, Taibah UniversityDépartement de pathologie, Université de SherbrookePrincess Margaret Cancer CentreDepartment of Laboratory Medicine and Pathobiology, University of TorontoDepartment of Laboratory Medicine and Pathobiology, University of TorontoDepartment of Pathology and Clinical Laboratory Medicine, King Fahad Medical CityDepartment of Pathology, College of Medicine, Imam Abdulrahman Bin Faisal UniversityDepartment of Pathology, College of Medicine, Imam Abdulrahman Bin Faisal UniversityLaboratory Medicine Program, Department of Pathology, University Health Network, 200 Elizabeth StreetDepartment of Laboratory Medicine and Pathobiology, University of TorontoAxe neurosciences du Centre de recherche du Centre hospitalier universitaire (CHU) de Québec-Université Laval, et Département de biologie moléculaire, biochimie et pathologie de l’Université LavalInstituto D’Or de Pesquisa e Ensino (IDOR)Department of Laboratory Medicine and Pathobiology, University of TorontoPrincess Margaret Cancer CentreAbstract Deep learning has proven capable of automating key aspects of histopathologic analysis. However, its context-specific nature and continued reliance on large expert-annotated training datasets hinders the development of a critical mass of applications to garner widespread adoption in clinical/research workflows. Here, we present an online collaborative platform that streamlines tissue image annotation to promote the development and sharing of custom computer vision models for PHenotyping And Regional Analysis Of Histology (PHARAOH; https://www.pathologyreports.ai/ ). Specifically, PHARAOH uses a weakly supervised, human-in-the-loop learning framework whereby patch-level image features are leveraged to organize large swaths of tissue into morphologically-uniform clusters for batched annotation by human experts. By providing cluster-level labels on only a handful of cases, we show how custom PHARAOH models can be developed efficiently and used to guide the quantification of cellular features that correlate with molecular, pathologic and patient outcome data. Moreover, by using our PHARAOH pipeline, we showcase how correlation of cohort-level cytoarchitectural features with accompanying biological and outcome data can help systematically devise interpretable morphometric models of disease. Both the custom model design and feature extraction pipelines are amenable to crowdsourcing, positioning PHARAOH to become a fully scalable, systems-level solution for the expansion, generalization and cataloging of computational pathology applications.https://doi.org/10.1038/s41467-024-55780-z
spellingShingle Kevin Faust
Min Li Chen
Parsa Babaei Zadeh
Dimitrios G. Oreopoulos
Alberto J. Leon
Ameesha Paliwal
Evelyn Rose Kamski-Hennekam
Marly Mikhail
Xianpi Duan
Xianzhao Duan
Mugeng Liu
Narges Ahangari
Raul Cotau
Vincent Francis Castillo
Nikfar Nikzad
Richard J. Sugden
Patrick Murphy
Safiyh S. Aljohani
Philippe Echelard
Susan J. Done
Kiran Jakate
Zaid Saeed Kamil
Yazeed Alwelaie
Mohammed J. Alyousef
Noor Said Alsafwani
Assem Saleh Alrumeh
Rola M. Saleeb
Maxime Richer
Lidiane Vieira Marins
George M. Yousef
Phedias Diamandis
PHARAOH: A collaborative crowdsourcing platform for phenotyping and regional analysis of histology
Nature Communications
title PHARAOH: A collaborative crowdsourcing platform for phenotyping and regional analysis of histology
title_full PHARAOH: A collaborative crowdsourcing platform for phenotyping and regional analysis of histology
title_fullStr PHARAOH: A collaborative crowdsourcing platform for phenotyping and regional analysis of histology
title_full_unstemmed PHARAOH: A collaborative crowdsourcing platform for phenotyping and regional analysis of histology
title_short PHARAOH: A collaborative crowdsourcing platform for phenotyping and regional analysis of histology
title_sort pharaoh a collaborative crowdsourcing platform for phenotyping and regional analysis of histology
url https://doi.org/10.1038/s41467-024-55780-z
work_keys_str_mv AT kevinfaust pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT minlichen pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT parsababaeizadeh pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT dimitriosgoreopoulos pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT albertojleon pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT ameeshapaliwal pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT evelynrosekamskihennekam pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT marlymikhail pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT xianpiduan pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT xianzhaoduan pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT mugengliu pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT nargesahangari pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT raulcotau pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT vincentfranciscastillo pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT nikfarnikzad pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT richardjsugden pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT patrickmurphy pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT safiyhsaljohani pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT philippeechelard pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT susanjdone pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT kiranjakate pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT zaidsaeedkamil pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT yazeedalwelaie pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT mohammedjalyousef pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT noorsaidalsafwani pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT assemsalehalrumeh pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT rolamsaleeb pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT maximericher pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT lidianevieiramarins pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT georgemyousef pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology
AT phediasdiamandis pharaohacollaborativecrowdsourcingplatformforphenotypingandregionalanalysisofhistology